I am evaluating retail search. With regard to semantic search, I saw some out-of-the-box impressive features, for example. the famous search phrase: long sleeve short baby shower dress.
But each application is different, there are some specifics. Application developers are happy to provide sample data to train (or fine-tune) the model, anyway to do that ?
An hypothetical example, products like below:
2022 Chevy Camaro, with mileage of 8,000, and 20 MPG
2015 Chevy Cruze, with mileage of 40,000, and 32 MPG
The search terms such "less than 5 year old cars", "under 10,000 miles", or "30 MPG or higher" do not work, I tried.
Anyway to do 'few-shots" training? we are happy to provide data, though it should be only for our application.
LinkedIn
Twitter
